List your company
ResearchFormerly WizWand

Open-ended Visual Question Answering on PMC-VQA (test)

36.8AccuracyMedVInT-TE
20.26424.55728.8533.143May 17, 2023
Updated 8mo ago

Evaluation results

MethodLinks
MedVInT-TELanguage Backbone=LLAMA-ENC, Vision Backbone=PMC-CLIP, Protocol=Trained on PMC-VQA2023.0536.818.4
MedVInT-TELanguage Backbone=PubMedBERT, Vision Backbone=PMC-CLIP, Protocol=Trained on PMC-VQA2023.0536.423.2
MedVInT-TELanguage Backbone=PMC-LLAMA-ENC, Vision Backbone=PMC-CLIP, Protocol=Trained on PMC-VQA2023.0535.318.6
MedVInT-TELanguage Backbone=PMC-LLAMA-ENC, Vision Backbone=Scratch, Protocol=Trained on PMC-VQA2023.053517
MedVInT-TELanguage Backbone=PubMedBERT, Vision Backbone=CLIP, Protocol=Trained on PMC-VQA2023.0534.420.8
MedVInT-TELanguage Backbone=PMC-LLAMA-ENC, Vision Backbone=CLIP, Protocol=Trained on PMC-VQA2023.0534.416.5
MedVInT-TELanguage Backbone=PubMedBERT, Vision Backbone=Scratch, Protocol=Trained on PMC-VQA2023.0534.220.9
MedVInT-TDLanguage Backbone=PMC-LLAMA, Vision Backbone=PMC-CLIP, Protocol=Trained on PMC-VQA2023.0533.621.5
MedVInT-TELanguage Backbone=LLAMA-ENC, Vision Backbone=CLIP, Protocol=Trained on PMC-VQA2023.0533.415.1
MedVInT-TDLanguage Backbone=LLAMA, Vision Backbone=PMC-CLIP, Protocol=Trained on PMC-VQA2023.0533.421.3
MedVInT-TDLanguage Backbone=PMC-LLAMA, Vision Backbone=CLIP, Protocol=Trained on PMC-VQA2023.0532.620.4
MedVInT-TELanguage Backbone=LLAMA-ENC, Vision Backbone=Scratch, Protocol=Trained on PMC-VQA2023.0532.515.9
MedVInT-TDLanguage Backbone=LLAMA, Vision Backbone=CLIP, Protocol=Trained on PMC-VQA2023.0532.220
MedVInT-TDLanguage Backbone=LLAMA, Vision Backbone=Scratch, Protocol=Trained on PMC-VQA2023.0530.218
MedVInT-TDLanguage Backbone=PMC-LLAMA, Vision Backbone=Scratch, Protocol=Trained on PMC-VQA2023.0529.817.4
LLAVA-MedLanguage Backbone=Vicuna, Vision Backbone=BioMedCLIP, Protocol=Zero-shot2023.0529.43.9
LLAMALanguage Backbone=LLAMA, Vision Backbone=None, Protocol=Language-only2023.0527.214.6
Open-FlamingoLanguage Backbone=LLAMA, Vision Backbone=CLIP, Protocol=Zero-shot2023.0526.54.1
MedICap-PMCVQA-GPT-4Language Backbone=GPT-4, Vision Backbone=MedICap-PMCVQA, Protocol=Trained on PMC-VQA2023.0522.43.8
GPT-4-OracleLanguage Backbone=GPT-4, Vision Backbone=None, Protocol=Language-only2023.052218.8
BLIP-2Language Backbone=OPT-2.7B, Vision Backbone=CLIP, Protocol=Zero-shot2023.0521.87.6
GPT-4Language Backbone=GPT-4, Vision Backbone=None, Protocol=Language-only2023.0521.13
MedICap-GPT-4Language Backbone=GPT-4, Vision Backbone=MedICap, Protocol=Zero-shot2023.0520.94.2